Hydrogen fuel cell vehicle ultra-low temperature cold start thermal management system

Abstract

This invention discloses an ultra-low temperature cold start thermal management system for hydrogen fuel cell vehicles, relating to the field of thermal management technology for hydrogen fuel cell vehicles. It includes a thermal management platform, which is communicatively connected to the following modules: a temperature monitoring and prediction module, used to monitor the temperature of key internal components of the hydrogen fuel cell using temperature sensors and, in conjunction with a temperature prediction model, predict the temperature change trend inside the fuel cell. This invention utilizes high-precision temperature sensors and a long short-term memory network model to predict the internal temperature change trend of the fuel cell in advance, dynamically adjusting the heating power to ensure that the battery rapidly warms up to a suitable operating temperature in ultra-low temperature environments. This avoids start-up difficulties caused by localized overcooling, significantly shortens the low-temperature start-up time, improves the reliability and stability of the system in extreme environments, and ensures the normal operation of hydrogen fuel cell vehicles in cold regions.

Description

Technical Field

[0001] This invention relates to the field of thermal management technology for hydrogen fuel cell vehicles, and specifically to an ultra-low temperature cold start thermal management system for hydrogen fuel cell vehicles. Background Technology

[0002] Hydrogen fuel cells generate electricity through the chemical reaction of hydrogen and oxygen, releasing water and heat in the process. Hydrogen is first stored and then converted into electricity through an electrochemical reaction in the fuel cell stack. This process depends on suitable temperature conditions. Hydrogen fuel cell vehicles (FCEVs) are considered an important direction for the future development of automobiles due to their zero emissions, long driving range, and high efficiency. However, the performance of hydrogen fuel cell vehicles in low-temperature environments remains one of the challenges for technological development, especially the cold start problem.

[0003] In existing technologies, under ultra-low temperature conditions, thermal management systems struggle to precisely control the internal temperature of fuel cells, leading to localized overheating or overcooling, which affects battery performance and lifespan. Furthermore, the system's response to temperature changes is delayed, making it impossible to adjust heating or cooling strategies in a timely manner, resulting in a decline in battery performance during the initial startup phase. Therefore, how to predict temperature changes, dynamically adjust heating and cooling strategies, and shorten the system's response time to temperature changes is the problem this invention aims to solve. To this end, an ultra-low temperature cold start thermal management system for hydrogen fuel cell vehicles is proposed. Summary of the Invention

[0004] The purpose of this invention is to provide an ultra-low temperature cold start thermal management system for hydrogen fuel cell vehicles to solve the problems mentioned in the background art.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0006] A thermal management system for ultra-low temperature cold start of a hydrogen fuel cell vehicle includes a thermal management platform, wherein the thermal management platform is communicatively connected to the following modules:

[0007] The temperature monitoring and prediction module is used to monitor the temperature of key parts inside the hydrogen fuel cell using temperature sensors, and combined with a temperature prediction model to predict the temperature change trend inside the fuel cell.

[0008] The thermal management control module is used to dynamically adjust the heating system and cooling system according to the output of the temperature monitoring and prediction module, and to perform heating or cooling operations.

[0009] The temperature response adjustment module is used to monitor and quickly adjust temperature changes in real time using an adaptive control response algorithm, thereby shortening the system's response time to temperature changes.

[0010] The actuator response module is used to optimize the response speed of the actuators in the heating and cooling system, adjust the working state after receiving the control signal, reduce temperature fluctuations caused by actuator response delay, and improve the overall system performance.

[0011] A further improvement of the technical solution of the present invention is that the temperature monitoring and prediction module includes a real-time temperature monitoring unit and a temperature prediction unit;

[0012] The real-time temperature monitoring unit is used to collect the temperature of key parts inside the hydrogen fuel cell using a high-precision temperature sensor, obtain real-time temperature data, and provide accurate input for the temperature prediction and control system.

[0013] The temperature prediction unit, based on data collected by temperature sensors and combined with the thermal model and historical operating data of the fuel cell, uses a long short-term memory network to predict the future trend of internal temperature changes in the fuel cell.

[0014] A further improvement to the technical solution of the present invention is that the real-time temperature monitoring unit specifically includes:

[0015] High-precision temperature sensors are distributed and deployed in key parts of the hydrogen fuel cell. The temperature sensors are initialized and calibrated to ensure their measurement accuracy. At the same time, the connection status of the sensors is checked to ensure that the data transmission channel is unobstructed so as to measure the temperature of the target area. The initial calibration includes zero-point calibration, gain calibration and connection status check.

[0016] Sensors collect temperature data from key components inside the hydrogen fuel cell in real time and transmit it to the thermal management platform via a high-bandwidth communication interface (CAN bus). The collected temperature data undergoes preprocessing, including filtering to eliminate noise interference, normalization to unify dimensions, and timestamp to ensure data timeliness while preserving temperature change trends. The output voltage or resistance values ​​of the temperature sensors are converted into standard temperature values, and dimensions are unified for subsequent analysis. A high-precision timestamp is added to each data point to ensure data timeliness and synchronization with multiple sensors. Finally, the preprocessed temperature data is stored in a temporary buffer for temporary storage.

[0017] A further improvement to the technical solution of the present invention is that the temperature prediction unit specifically includes:

[0018] The system receives real-time temperature data from key internal components of the hydrogen fuel cell from temperature sensors. Simultaneously, it loads a fuel cell thermal model containing parameters such as heat capacity, thermal resistance, and heat transfer coefficient, as well as a historical operating database covering temperature-power mapping relationships under different operating conditions. Through timestamp alignment technology, it maps the timestamps of the sensor data with the thermal model calculation results and historical data records to a unified time-series coordinate system. It extracts multi-dimensional feature vectors, including the current temperature gradient, historical temperature fluctuation rate, power load change rate, and ambient temperature correction term, and constructs a feature matrix to characterize the dynamic characteristics of the system.

[0019] The feature matrix is ​​input into a temperature prediction model trained on a long short-term memory network model. The model captures long-term dependencies and short-term fluctuation patterns in the time series through multi-layer gating units. Combined with the constraint of the maximum allowable temperature rise rate in the thermal model, the model predicts future temperature changes. The future temperature change prediction adopts a sliding window mechanism, which generates a temperature trend curve for the next 5-10 seconds starting from the current time. The output is structured data containing the predicted value and its confidence interval.

[0020] The temperature prediction results output by the temperature prediction model are verified to check whether the prediction results meet the constraints of the thermal model. The predicted temperature trend is compared with historical data under similar operating conditions to evaluate the deviation range. The prediction results that pass the verification are marked as valid and transmitted to the thermal management control module for dynamic adjustment of the heating power strategy to reduce the temperature fluctuation range.

[0021] A further improvement of the technical solution of the present invention is that the thermal management control module includes a heating power adjustment unit and a cooling system adjustment unit;

[0022] The heating power adjustment unit is used to dynamically adjust the power output of the heating system based on the temperature prediction results, so as to ensure that the fuel cell can quickly heat up to the appropriate operating temperature in the initial stage of startup.

[0023] The cooling system adjustment unit is used to automatically activate the cooling system and adjust the cooling parameters of the cooling system to cool the fuel cell during operation, based on temperature prediction results, in order to prevent overheating and damage to the battery.

[0024] A further improvement to the technical solution of the present invention is that the heating power adjustment unit specifically includes:

[0025] The system receives output data from the temperature monitoring and prediction module, including the trend curve of the internal temperature of the fuel cell within the next 5-10 seconds and its confidence interval. It then analyzes the output data of the temperature monitoring and prediction module, extracts the slope and extreme points of the predicted temperature curve, and calculates the remaining temperature difference and time window from the current temperature to the target temperature by combining the thermal model constraints. The slope of the predicted temperature curve is the heating rate, which represents the current heating trend. The extreme points are the moments of the lowest temperature, which identify local overcooling risk areas. The thermal model constraint is that the maximum allowable temperature rise rate is ≤5℃ / s.

[0026] According to the target heating trajectory, the regulating unit dynamically adjusts the power output of the heating system through a closed-loop control strategy. Among them, a multi-region collaborative control algorithm is adopted to allocate the total heating power to the key parts of the hydrogen fuel cell as needed. Based on the deviation between the real-time temperature of each region and the target trajectory, the power allocation weight is optimized by weighted least squares method to ensure that the temperature difference between each region is ≤2℃.

[0027] The heating power adjustment effect is evaluated from multiple dimensions. The integral of the deviation between the actual heating trajectory and the target trajectory is calculated to quantify the heating efficiency and energy utilization efficiency. If the evaluation results show that the deviation exceeds the preset deviation threshold, the control parameters are optimized to improve the adjustment accuracy. If an abnormality is detected in the heating system, that is, the power output deviation from the command is >10%, the redundant heating module switching or safety shutdown mechanism is triggered to ensure the reliability of the system.

[0028] A further improvement to the technical solution of the present invention is that the cooling system adjustment unit specifically includes:

[0029] The system receives the temperature trend curve and confidence interval for the next 5-10 seconds from the temperature monitoring and prediction module, extracts the heating rate and extreme points. For the heating rate, the slope of the temperature curve is calculated using numerical differentiation to determine whether the cooling threshold (temperature rise rate > 3℃ / s) is triggered. For extreme points, the system locates the highest temperature moment in the temperature curve, identifies potential overheating risk areas, and determines whether the cooling system needs to be activated based on the thermal model constraints. If the predicted temperature exceeds the safety threshold of 75℃ or the temperature rise rate exceeds the limit, the cooling system is activated immediately. The system then calculates the remaining overheat amount and time window from the current temperature to the target temperature. Based on a fuzzy logic algorithm, the overheat amount and time window are mapped to the cooling demand level to determine the initial parameters of the cooling system, including fan speed, water pump flow rate, and coolant distribution.

[0030] An adaptive PID control algorithm is adopted to dynamically adjust cooling parameters based on the real-time deviation between predicted and actual temperatures. Specifically, for fan speed, the proportional term quickly responds to deviations to suppress temperature overshoot; for water pump flow, the integral term eliminates steady-state errors to ensure long-term cooling efficiency; and for coolant distribution, the differential term predicts deviation trends to optimize coolant flow distribution in each area. Combined with multi-area temperature sensor data, regional temperature difference constraints and cooling efficiency constraints are applied to the cooling parameters. For regional temperature difference constraints, the maximum temperature difference in each area is ensured to be ≤3℃ to avoid local thermal stress concentration; and for cooling efficiency constraints, the temperature difference between coolant and battery is limited to ≥10℃ to ensure heat exchange efficiency.

[0031] Calculate the integral of the deviation between the actual temperature trajectory and the target temperature trajectory, i.e., the root mean square error (RMSE). Analyze the cooling efficiency index and energy consumption index. For the cooling efficiency index, if RMSE ≤ 2℃, it is judged as high-efficiency cooling. For the energy consumption index, if the cooling energy consumption per unit temperature difference is ≤ 0.05kWh / ℃, it is judged as energy-saving operation. If the evaluation results show that the deviation exceeds the threshold, i.e., RMSE > 3℃, the strategy optimization mechanism is triggered.

[0032] A further improvement to the technical solution of the present invention is that the temperature response adjustment module specifically includes:

[0033] By integrating real-time data from multiple temperature sensors and combining it with the trend curve for the next 5-10 seconds output by the temperature prediction module, a dynamic temperature field model is constructed. Sensor noise is eliminated through a sliding window filtering algorithm, and temperature change features, including heating rate and extreme points, are extracted.

[0034] Temperature abrupt changes are determined based on the dynamic threshold method, which is divided into heating rate abrupt changes and extreme point shifts. For heating rate abrupt changes, if the rate of temperature change exceeds the historical mean ± 2 standard deviations, it is determined to be rapid heating or cooling. For extreme point shifts, if the deviation between the predicted temperature extreme point and the target trajectory exceeds a preset shift threshold, strategy adjustment is triggered.

[0035] The control mode is automatically switched according to the type of temperature change of heating / cooling. For temperature change, the rapid heating strategy is activated, and the power allocation weight of the heating system is increased first. For temperature change, the enhanced cooling strategy is activated, and the fan speed and water pump flow are increased first. The coolant distribution ratio is optimized. The control parameters, including proportional gain, integral time and derivative time, are dynamically adjusted by using a fuzzy PID algorithm.

[0036] Based on the integral of the deviation between the predicted temperature and the actual temperature, the control parameters are dynamically corrected by the gradient descent method. Combined with the regional temperature synchronization index, i.e. the temperature difference between each region is ≤2℃, the allocation of heating / cooling resources is optimized by the quadratic programming algorithm.

[0037] A further improvement to the technical solution of this invention lies in the following: the specific process of optimizing the allocation of heating / cooling resources is as follows:

[0038] The deviation between the predicted temperature and the actual temperature is continuously calculated, and the calculated deviation is integrated to obtain the deviation integral, so as to quantify the cumulative error.

[0039] An objective function is constructed based on the deviation integral to evaluate the difference between the control parameters and the actual temperature. The control parameters are iteratively optimized using the gradient descent method. Specifically, the gradient of the objective function with respect to the current control parameters is calculated to determine the direction of parameter adjustment. The control parameters are adjusted along the gradient direction to gradually reduce the deviation integral, improve control accuracy, and monitor the temperature change after adjustment in real time.

[0040] A regional temperature synchronicity index is introduced, namely, the temperature difference between regions is ≤2℃, which is used as a constraint condition. At the same time, the allocation efficiency of heating / cooling resources is used as the objective function to construct a quadratic programming model.

[0041] The quadratic programming algorithm is used to solve the quadratic programming model and calculate the optimal heating / cooling resource allocation scheme. Based on the solution results, the heating power or cooling flow rate is allocated to each region to synchronize the temperature of each region and maintain the uniformity of the internal temperature field of the fuel cell.

[0042] A further improvement to the technical solution of the present invention is that the actuator response module specifically includes:

[0043] The actuator response module receives control signals from the thermal management control module in real time, including power adjustment commands for the heating or cooling system. It preprocesses the received control signals and checks their integrity and validity, confirming whether the control signals conform to the expected command format and range. If the command fluctuation is less than 1% within 5 consecutive sampling periods, the current command value is locked. Multi-source signals are synchronized based on the system clock to avoid command conflicts. If the temperature change rate is greater than 2℃ / s, the heating / cooling intensity command is responded to first. If the regional temperature difference is greater than 1.5℃, the resource allocation command is responded to first.

[0044] The processed control signal is converted into a specific drive signal to adjust the working state of the actuators in the heating and cooling systems. For the actuators in the heating system, rapid heating is achieved by changing the power output of the heating element. For the actuators in the cooling system, rapid cooling is achieved by adjusting the fan speed and water pump flow parameters.

[0045] The system continuously monitors the actual operating status of the actuator, including power output, speed, and flow parameters. The status information is fed back to the thermal management control module in real time through a feedback loop. The difference between the actual status and the target status is compared, and the actuator's drive parameters are dynamically optimized using an adaptive control algorithm to ensure the actuator's response speed and accuracy. At the same time, the system monitors the actuator's operating status in real time, detects and handles any faults or abnormalities, and ensures the long-term stable operation of the actuator.

[0046] Due to the adoption of the above technical solution, the technical progress achieved by this invention compared to the prior art is as follows:

[0047] 1. This invention provides an ultra-low temperature cold start thermal management system for hydrogen fuel cell vehicles. By utilizing high-precision temperature sensors and a long short-term memory network model, the system predicts the internal temperature change trend of the fuel cell in advance and dynamically adjusts the heating power to ensure that the battery can quickly heat up to the suitable operating temperature in ultra-low temperature environments. This avoids starting difficulties caused by local overcooling, significantly shortens the low-temperature start-up time, improves the reliability and stability of the system in extreme environments, and ensures the normal operation of hydrogen fuel cell vehicles in cold regions.

[0048] 2. This invention provides an ultra-low temperature cold start thermal management system for hydrogen fuel cell vehicles. Based on temperature prediction results, it precisely adjusts the power output of the heating and cooling systems to avoid energy waste. Through a PID control parameter dynamic tuning algorithm and a multi-region collaborative control algorithm, the system can allocate heating power as needed, ensuring that the fuel cell heats up quickly in the initial stage of startup while reducing unnecessary energy consumption. In addition, the adaptive PID control algorithm dynamically adjusts the cooling parameters during the cooling process, further improving energy utilization efficiency and extending the vehicle's driving range. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0050] Figure 1 This is a schematic diagram of the workflow of the present invention;

[0051] Figure 2 This is a schematic diagram of the working process of the temperature response adjustment module of the present invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] Example 1, as Figure 1 , Figure 2 As shown, this invention provides an ultra-low temperature cold start thermal management system for hydrogen fuel cell vehicles, including a thermal management platform. The thermal management platform is communicatively connected to the following modules, wherein:

[0054] The temperature monitoring and prediction module is used to monitor the temperature of key components inside the hydrogen fuel cell using temperature sensors, and combined with a temperature prediction model to predict the temperature change trend inside the fuel cell. The temperature monitoring and prediction module includes a real-time temperature monitoring unit and a temperature prediction unit.

[0055] The real-time temperature monitoring unit utilizes high-precision temperature sensors to collect temperatures from key components inside the hydrogen fuel cell, obtaining real-time temperature data to provide accurate input for the temperature prediction and control system. High-precision temperature sensors (platinum resistance thermometers or thermocouples) are distributed across key components of the hydrogen fuel cell (membrane electrode, gas diffusion layer, cooling channel interface), ensuring close contact between the sensors and the target area for accurate measurement. The unit performs initial calibration of the temperature sensors to ensure measurement accuracy and checks the sensor connectivity to ensure unobstructed data transmission channels for measuring the temperature of the target area. The initial calibration includes zero-point calibration, gain calibration, and connectivity checks. Zero-point calibration adjusts the temperature sensor output to the theoretical zero-point value under a known reference temperature environment to eliminate static errors. Gain calibration corrects the temperature sensor output slope through multi-temperature point calibration. To ensure full-range measurement accuracy, a connection status check verifies the physical connection and electrical parameters of the temperature sensor and communication interface, ensuring no open or short circuits in the data transmission channel. The sensor collects temperature data from key components inside the hydrogen fuel cell in real time and transmits it to the thermal management platform via a high-bandwidth communication interface (CAN bus). The collected temperature data undergoes preprocessing, including filtering to eliminate noise interference, normalization to unify dimensions, and timestamp marking to ensure data timeliness. A first-order low-pass filter algorithm (cutoff frequency set according to system dynamic response requirements) is used to eliminate high-frequency noise while preserving temperature change trends. The output voltage or resistance value of the temperature sensor is converted into a standard temperature value, unifying dimensions for subsequent analysis. A high-precision timestamp is added to each data point to ensure data timeliness and multi-sensor synchronization. The preprocessed temperature data is then stored in a temporary buffer for temporary storage.

[0056] The temperature prediction unit, based on data collected by temperature sensors and combined with the fuel cell's thermal model and historical operating data, uses a long short-term memory network to predict future temperature trends inside the fuel cell. This allows for advance temperature prediction, providing proactive guidance for dynamically adjusting heating power and reducing temperature fluctuations. It receives real-time temperature data from key components inside the hydrogen fuel cell, simultaneously loading a fuel cell thermal model containing parameters such as heat capacity, thermal resistance, and heat transfer coefficient, as well as a historical operating database covering temperature-power mapping relationships under different operating conditions. Through timestamp alignment technology, it maps the timestamps of the sensor data with the thermal model calculation results and historical data records to a unified time-series coordinate system, extracting multi-dimensional feature vectors, including current... A feature matrix is ​​constructed to characterize the system's dynamic properties, incorporating temperature gradient, historical temperature fluctuation rate, power load change rate, and ambient temperature correction term. Rows correspond to time steps, and columns correspond to feature dimensions. The current temperature gradient is the first / second time derivative used to calculate the real-time temperature of key components, representing the transient thermal change rate. Historical temperature fluctuation rate is the standard deviation or range of temperatures over the past 30 seconds, calculated using a sliding window, quantifying thermal stability. The power load change rate is the slope used to analyze the stack's output power, correlated with the heat generation rate. The ambient temperature and humidity are introduced as external variables, and feature weights are adjusted using a thermal model correction factor. The feature matrix is ​​then input into a temperature prediction model trained on a long short-term memory network architecture. This model uses multiple gating units to capture long-term dependencies and short-term fluctuation patterns in time series data. Combined with the constraint of the maximum allowable rate of temperature rise in the thermal model, it predicts future temperature changes. The future temperature change prediction employs a sliding window mechanism, generating a temperature trend curve for the next 5-10 seconds starting from the current time. The output is structured data containing the predicted values ​​and their confidence intervals. The model architecture includes an input layer, hidden layers, and fully connected layers. The input layer is a standardized feature matrix (mean 0, variance 1). The hidden layers are two-layer LSTM units (64 / 128 neurons per layer), using forget gates, input gates, and output gates to capture long-term dependencies (such as thermal inertia effects) and short-term fluctuations (such as power spikes). The fully connected layers... The LSTM output is mapped to the temperature prediction value for the next 5-10 seconds. Dropout (0.2) is used to prevent overfitting. The temperature prediction results output by the temperature prediction model are verified to check whether the prediction results meet the thermal model constraints. The predicted temperature trend is compared with historical data under similar working conditions to evaluate the deviation range. The prediction results that pass the verification are marked as valid and transmitted to the thermal management control module for dynamic adjustment of the heating power strategy to reduce the temperature fluctuation amplitude. In particular, the predicted temperature trend is aligned with historical data under similar working conditions through the dynamic time warping algorithm, the Euclidean distance deviation threshold is calculated, and the confidence score is generated by combining the verification results. If the score is lower than the threshold, the model is retrained or data is supplemented.

[0057] The thermal management control module is used to dynamically adjust the heating system and cooling system based on the output of the temperature monitoring and prediction module to perform heating or cooling operations. The thermal management control module includes a heating power adjustment unit and a cooling system adjustment unit.

[0058] The heating power regulation unit dynamically adjusts the power output of the heating system based on temperature prediction results. This ensures the fuel cell rapidly heats up to a suitable operating temperature during startup, avoiding startup difficulties caused by localized overcooling, reducing energy waste, and improving energy utilization efficiency. It receives output data from the temperature monitoring and prediction module, including the trend curve of the fuel cell's internal temperature change over the next 5-10 seconds and its confidence interval. The unit analyzes this output data, extracting the slope and extreme points of the predicted temperature curve. Combined with thermal model constraints, it calculates the remaining temperature difference and time window from the current temperature to the target temperature. The slope of the predicted temperature curve represents the heating rate, indicating the current heating trend. The extreme points represent the lowest temperature moments, identifying areas of localized overcooling risk. The thermal model constraint is a maximum allowable temperature rise rate ≤ 5℃ / s. Based on the remaining temperature difference and time window, a target heating trajectory is generated using a PID control parameter dynamic tuning algorithm. This ensures the fuel cell rapidly and smoothly heats up to a suitable operating temperature during startup, avoiding localized overcooling due to slow heating or thermal stress damage to the material due to excessively rapid heating. Based on the target heating trajectory, the regulating unit dynamically adjusts the power output of the heating system through a closed-loop control strategy. A multi-region collaborative control algorithm is employed to allocate the total heating power to key components of the hydrogen fuel cell as needed. Based on the deviation between the real-time temperature of each region and the target trajectory, the power allocation weights are optimized using a weighted least squares method to ensure that the temperature difference between regions is ≤2℃, guaranteeing temperature synchronization. Based on the real-time deviation between the predicted and actual temperatures, an adaptive PID algorithm dynamically adjusts the heating power to achieve precise matching between the heating rate and the target trajectory. Combining thermal model and temperature sensor data, multi-level constraints are applied to the heating power to avoid energy waste or localized overheating due to power overload. The heating power regulation effect is evaluated from multiple dimensions, calculating the integral of the deviation between the actual heating trajectory and the target trajectory (root mean square error RMSE) to quantify heating efficiency and energy utilization efficiency. If the evaluation results show that the deviation exceeds a preset deviation threshold, the control parameters are optimized to improve regulation accuracy. If an abnormality is detected in the heating system, i.e., the power output deviation from the command is >10%, a redundant heating module switching or safety shutdown mechanism is triggered to ensure system reliability.

[0059] The cooling system adjustment unit automatically activates the cooling system and adjusts its cooling parameters to reduce temperature during fuel cell operation based on temperature prediction results. This prevents overheating and battery damage, ensures uniform temperature distribution within the fuel cell, extends battery life, and improves system reliability. It receives the temperature trend curve and confidence interval for the next 5-10 seconds from the temperature monitoring and prediction module, extracts the heating rate and extreme points. For the heating rate, it calculates the slope of the temperature curve using numerical differentiation to determine if a cooling threshold (temperature rise rate > 3℃ / s) is triggered. For extreme points, it locates the highest temperature moment on the temperature curve, identifies potential overheating risk areas, and, combined with thermal model constraints, determines whether the cooling system needs to be activated. If the predicted temperature exceeds the 75℃ safety threshold or the temperature rise rate exceeds the limit, the cooling system is immediately activated. It then calculates the remaining overheat amount and time window from the current temperature to the target temperature. Based on a fuzzy logic algorithm, it maps the overheat amount and time window to a cooling demand level, determines the initial parameters of the cooling system, including fan speed, water pump flow rate, and coolant distribution, and employs an adaptive PI... The D control algorithm dynamically adjusts cooling parameters based on the real-time deviation between predicted and actual temperatures. Specifically, for fan speed, a proportional term is used to quickly respond to deviations and suppress temperature overshoot. For water pump flow, an integral term is used to eliminate steady-state errors and ensure long-term cooling efficiency. For coolant distribution, a differential term is used to predict deviation trends and optimize coolant flow distribution in each region. Combining data from multiple temperature sensors, regional temperature difference constraints and cooling efficiency constraints are applied to the cooling parameters. For regional temperature difference constraints, the maximum temperature difference in each region is ensured to be ≤3℃ to avoid localized thermal stress concentration. For cooling efficiency constraints, the temperature difference between the coolant and battery is limited to ≥10℃ to ensure heat exchange efficiency. The algorithm calculates the integral of the deviation between the actual and target temperature trajectories, i.e., the root mean square error (RMSE), and analyzes cooling efficiency and energy consumption indicators. For cooling efficiency, RMSE ≤ 2℃ is considered high-efficiency cooling. For energy consumption, cooling energy consumption per unit temperature difference is ≤0.05kWh / ℃, indicating energy-saving operation. If the evaluation results show a deviation exceeding the threshold (RMSE > 3℃), a strategy optimization mechanism is triggered.

[0060] The temperature response adjustment module is used to monitor and quickly adjust temperature changes in real time using an adaptive control response algorithm, shortening the system's response time to temperature changes and ensuring that heating or cooling strategies can be adjusted in a timely manner when there are sudden temperature changes to maintain battery performance.

[0061] The actuator response module is used to optimize the response speed of the actuators in the heating and cooling system. After receiving the control signal, it adjusts the working state, reduces temperature fluctuations caused by actuator response delay, and improves the overall system performance.

[0062] Example 2, as Figure 1 , Figure 2As shown, based on Embodiment 1, the present invention provides a technical solution: Preferably, the temperature response adjustment module specifically includes:

[0063] Real-time data from multiple temperature sensors is integrated, combined with a trend curve for the next 5-10 seconds output from a temperature prediction module, to construct a dynamic temperature field model. A sliding window filtering algorithm is used to eliminate sensor noise, extracting temperature change features including heating rate and extreme points. Temperature abrupt changes are determined based on a dynamic threshold method, categorized into heating rate abrupt changes and extreme point shifts. For heating rate abrupt changes, if the temperature change rate exceeds the historical mean ± 2 standard deviations, it is determined to be a rapid heating or cooling. For extreme point shifts, if the deviation between the predicted temperature extreme point and the target trajectory exceeds a preset shift threshold, strategy adjustment is triggered. A Kalman filter is used to estimate the state of the abrupt change signal, filtering out false alarms. The control mode is automatically switched according to the type of temperature abrupt change (heating / cooling). For sudden temperature changes, a rapid heating strategy is activated, prioritizing the increase of the power allocation weight of the heating system. For sudden temperature changes, an enhanced cooling strategy is activated, prioritizing the increase of fan speed and water pump flow, and optimizing the coolant distribution ratio. A fuzzy PID algorithm is used to dynamically adjust the control parameters, including proportional gain, integral time, and derivative time. Specifically, for the proportional gain, a linear mapping is used based on the magnitude of the sudden temperature change to accelerate the response. For the integral time, dynamic adjustment is used based on the system inertia to suppress overshoot. For the derivative time, adaptive change is used based on the rate of sudden temperature change to predict the temperature change trend. Based on the integral of the deviation between the predicted temperature and the actual temperature, the control parameters are dynamically corrected using the gradient descent method. Combined with the regional temperature synchronization index, i.e., the temperature difference between each region is ≤2℃, the allocation of heating / cooling resources is optimized using a quadratic programming algorithm.

[0064] Furthermore, the specific process for optimizing the allocation of heating / cooling resources is as follows:

[0065] The deviation between the predicted temperature and the actual temperature is continuously calculated, and the calculated deviation is integrated to obtain the deviation integral, which quantifies the accumulated error. The deviation integral reflects the overall error level in the temperature control process. Based on the deviation integral, an objective function is constructed to evaluate the difference between the control parameters and the actual temperature. The control parameters are iteratively optimized using the gradient descent method. Specifically, the gradient of the objective function with respect to the current control parameters is calculated to determine the direction of parameter adjustment. The control parameters are adjusted along the gradient direction to gradually reduce the deviation integral, improve control accuracy, and monitor the temperature change after adjustment in real time to ensure that the parameter correction is effective and the system is stable. A regional temperature synchronization index is introduced, i.e., the temperature difference between each region is ≤2℃, which is used as a constraint condition. At the same time, the allocation efficiency of heating / cooling resources is used as the objective function to construct a quadratic programming model. The goal of the model is to optimize resource allocation and ensure that the temperature of each region is uniform and consistent with the target temperature. The quadratic programming algorithm is used to solve the quadratic programming model to calculate the optimal heating / cooling resource allocation scheme. Based on the solution results, the heating power or cooling flow rate is allocated to each region to synchronize the temperature of each region and maintain the uniformity of the internal temperature field of the fuel cell.

[0066] The actuator response module specifically includes:

[0067] The actuator response module receives control signals from the thermal management control module in real time, including power adjustment commands for the heating or cooling system. It preprocesses the received control signals, including signal parsing and filtering to remove potential noise interference, ensuring signal accuracy and reliability. Simultaneously, it checks the integrity and validity of the signals, confirming that the control signals conform to the expected command format and range. Specifically, if the command fluctuation is <1% within five consecutive sampling periods, the current command value is locked. Multi-source signals are synchronized based on the system clock to avoid command conflicts. If the temperature change rate is >2℃ / s, heating / cooling intensity commands are prioritized; if the regional temperature difference is >1.5℃, resource allocation commands are prioritized. The processed control signals are converted into specific drive signals to adjust the operating state of the actuators in the heating and cooling systems. For the heating system actuators... The actuators achieve rapid heating by changing the power output of the heating element. For the actuators in the cooling system, rapid cooling is achieved by adjusting the fan speed and water pump flow parameters. Specifically, for fan speed control, a PID controller converts the target speed into the motor drive voltage. For water pump flow control, a lookup table method is used to map the target flow rate to the water pump duty cycle, and pressure feedforward compensation is introduced. The actual operating status of the actuators, including power output, speed, and flow parameters, is continuously monitored. The status information is fed back to the thermal management control module in real time through a feedback loop. The difference between the actual state and the target state is compared, and the actuator drive parameters are dynamically optimized using an adaptive control algorithm to ensure the actuator's response speed and accuracy. At the same time, the operating status of the actuators is monitored in real time to detect and handle any faults or abnormalities, ensuring the long-term stable operation of the actuators.

[0068] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A thermal management system for ultra-low temperature cold start of a hydrogen fuel cell vehicle, comprising a thermal management platform, characterized in that: The thermal management platform has the following communication modules, among which: The temperature monitoring and prediction module is used to monitor the temperature of key components inside the hydrogen fuel cell using temperature sensors, and combined with a temperature prediction model, to predict the trend of temperature change inside the fuel cell. The thermal management control module is used to dynamically adjust the heating and cooling systems based on the output of the temperature monitoring and prediction module, to perform heating or cooling operations. The temperature response adjustment module is used to monitor and quickly adjust temperature changes in real time using an adaptive control response algorithm, thereby shortening the system's response time to temperature changes. The actuator response module is used to optimize the response speed of the actuators in the heating and cooling system and adjust the working state after receiving the control signal. The temperature monitoring and prediction module includes a real-time temperature monitoring unit and a temperature prediction unit; The real-time temperature monitoring unit is used to collect the temperature of key parts inside the hydrogen fuel cell using a temperature sensor to obtain real-time temperature data. The temperature prediction unit, based on the data collected by the temperature sensor, combined with the thermal model of the fuel cell and historical operating data, uses a long short-term memory network to predict the future trend of internal temperature changes in the fuel cell. The thermal management control module includes a heating power adjustment unit and a cooling system adjustment unit; The heating power adjustment unit is used to dynamically adjust the power output of the heating system based on the temperature prediction results. The cooling system adjustment unit is used to automatically activate the cooling system and adjust the cooling parameters of the cooling system to reduce the temperature during the operation of the fuel cell, based on the temperature prediction results. High-precision temperature sensors are distributed and deployed in key components of hydrogen fuel cells. According to the target heating trajectory, the regulating unit dynamically adjusts the power output of the heating system through a closed-loop control strategy. Among them, a multi-region collaborative control algorithm is adopted to allocate the total heating power to the key parts of the hydrogen fuel cell as needed. Based on the deviation between the real-time temperature of each region and the target trajectory, the power allocation weight is optimized by weighted least squares method to ensure that the temperature difference between each region is ≤2℃. An adaptive PID control algorithm is adopted to dynamically adjust the cooling parameters based on the real-time deviation between the predicted temperature and the actual temperature. Specifically, for the fan speed, the proportional term is used to quickly respond to the deviation; for the water pump flow rate, the integral term is used to eliminate the steady-state error; and for the coolant distribution, the differential term is used to predict the trend of deviation changes. Combined with multi-zone temperature sensor data, regional temperature difference constraints and cooling efficiency constraints are applied to the cooling parameters. For the regional temperature difference constraint, the maximum temperature difference in each zone is ensured to be ≤3℃. For the cooling efficiency constraint, the temperature difference between the coolant and the battery is limited to ≥10℃.

2. The ultra-low temperature cold start thermal management system for hydrogen fuel cell vehicles according to claim 1, characterized in that: The real-time temperature monitoring unit specifically includes: The temperature sensor is initialized and calibrated, and the connection status of the sensor is checked in order to measure the temperature of the target area. The initial calibration includes zero-point calibration, gain calibration and connection status check. The sensor collects temperature data from key parts inside the hydrogen fuel cell in real time and transmits it to the thermal management platform in real time through a high-bandwidth communication interface. The collected temperature data is preprocessed, including filtering to eliminate noise interference, normalization to unify the dimensions, and timestamp marking. At the same time, the temperature change trend is preserved, the output voltage or resistance value of the temperature sensor is converted into a standard temperature value, and a timestamp is added to each data point. The preprocessed temperature data is then stored in a temporary buffer for temporary storage.

3. The ultra-low temperature cold start thermal management system for hydrogen fuel cell vehicles according to claim 1, characterized in that: The temperature prediction unit specifically includes: The system receives real-time temperature data from key internal components of the hydrogen fuel cell from temperature sensors. Simultaneously, it loads a fuel cell thermal model containing parameters such as heat capacity, thermal resistance, and heat transfer coefficient, as well as a historical operating database covering temperature-power mapping relationships under different operating conditions. Through timestamp alignment technology, it maps the timestamps of the sensor data with the thermal model calculation results and historical data records to a unified time-series coordinate system. It extracts multi-dimensional feature vectors, including the current temperature gradient, historical temperature fluctuation rate, power load change rate, and ambient temperature correction term, and constructs a feature matrix to characterize the dynamic characteristics of the system. The feature matrix is ​​input into a temperature prediction model trained on a long short-term memory network model. The model captures long-term dependencies and short-term fluctuation patterns in the time series through multi-layer gating units. Combined with the constraint of the maximum allowable temperature rise rate in the thermal model, the model predicts future temperature changes. The future temperature change prediction adopts a sliding window mechanism, which generates a temperature trend curve for the next 5-10 seconds starting from the current time. The output is structured data containing the predicted value and its confidence interval. The temperature prediction results output by the temperature prediction model are verified to check whether the prediction results meet the constraints of the thermal model. The predicted temperature trend is compared with historical data under similar operating conditions to evaluate the deviation range. The prediction results that pass the verification are marked as valid and transmitted to the thermal management control module.

4. The ultra-low temperature cold start thermal management system for hydrogen fuel cell vehicles according to claim 1, characterized in that: The heating power adjustment unit specifically includes: The system receives output data from the temperature monitoring and prediction module, including the trend curve of the internal temperature of the fuel cell within the next 5-10 seconds and its confidence interval. It then analyzes the output data of the temperature monitoring and prediction module, extracts the slope and extreme points of the predicted temperature curve, and calculates the remaining temperature difference and time window from the current temperature to the target temperature by combining the thermal model constraints. The slope of the predicted temperature curve is the heating rate, which represents the current heating trend. The extreme points are the moments of the lowest temperature, which identify local overcooling risk areas. The thermal model constraint is that the maximum allowable temperature rise rate is ≤5℃ / s. The heating power adjustment effect is evaluated from multiple dimensions. The integral of the deviation between the actual heating trajectory and the target trajectory is calculated to quantify the heating efficiency and energy utilization efficiency. If the evaluation results show that the deviation exceeds the preset deviation threshold, the control parameters are optimized. If an abnormality is detected in the heating system, that is, the deviation between the power output and the command is >10%, the redundant heating module switching or safety shutdown mechanism is triggered.

5. The ultra-low temperature cold start thermal management system for hydrogen fuel cell vehicles according to claim 1, characterized in that: The cooling system regulating unit specifically includes: The system receives the temperature trend curve and confidence interval for the next 5-10 seconds from the temperature monitoring and prediction module, extracts the heating rate and extreme points. For the heating rate, the slope of the temperature curve is calculated by numerical differentiation to determine whether the cooling threshold is triggered. For extreme points, the highest temperature moment in the temperature curve is located to identify potential overheating risk areas. Combined with the thermal model constraints, it is determined whether the cooling system needs to be activated. If the predicted temperature exceeds the safety threshold of 75°C or the temperature rise rate exceeds the limit, the cooling system is activated immediately. Then, the remaining overheat amount and time window from the current temperature to the target temperature are calculated to determine the initial parameters of the cooling system, including fan speed, water pump flow rate, and coolant distribution. Calculate the integral of the deviation between the actual temperature trajectory and the target temperature trajectory, i.e., the root mean square error (RMSE). Analyze the cooling efficiency index and energy consumption index. For the cooling efficiency index, if RMSE ≤ 2℃, it is judged as high-efficiency cooling. For the energy consumption index, if the cooling energy consumption per unit temperature difference is ≤ 0.05kWh / ℃, it is judged as energy-saving operation. If the evaluation results show that the deviation exceeds the threshold, i.e., RMSE > 3℃, the strategy optimization mechanism is triggered.

6. The ultra-low temperature cold start thermal management system for hydrogen fuel cell vehicles according to claim 5, characterized in that: The temperature response adjustment module specifically includes: By integrating real-time data from multiple temperature sensors and combining it with the trend curve for the next 5-10 seconds output by the temperature prediction module, a dynamic temperature field model is constructed. Sensor noise is eliminated through a sliding window filtering algorithm, and temperature change features, including heating rate and extreme points, are extracted. Temperature abrupt changes are determined based on the dynamic threshold method, which is divided into heating rate abrupt changes and extreme point shifts. For heating rate abrupt changes, if the rate of temperature change exceeds the historical mean ± 2 standard deviations, it is determined to be rapid heating or cooling. For extreme point shifts, if the deviation between the predicted temperature extreme point and the target trajectory exceeds a preset shift threshold, strategy adjustment is triggered. The control mode is automatically switched according to the type of temperature change of heating / cooling. For temperature change, the rapid heating strategy is activated, and the power allocation weight of the heating system is increased first. For temperature change, the enhanced cooling strategy is activated, and the fan speed and water pump flow are increased first. The coolant distribution ratio is optimized. The control parameters, including proportional gain, integral time and derivative time, are dynamically adjusted by using a fuzzy PID algorithm. Based on the integral of the deviation between the predicted temperature and the actual temperature, the control parameters are dynamically corrected by the gradient descent method. Combined with the regional temperature synchronization index, i.e. the temperature difference between each region is ≤2℃, the allocation of heating / cooling resources is optimized by the quadratic programming algorithm.

7. The ultra-low temperature cold start thermal management system for hydrogen fuel cell vehicles according to claim 6, characterized in that: The specific process for optimizing the allocation of heating / cooling resources is as follows: The deviation between the predicted temperature and the actual temperature is continuously calculated, and the calculated deviation is integrated to obtain the deviation integral, so as to quantify the cumulative error. An objective function is constructed based on the deviation integral to evaluate the difference between the control parameters and the actual temperature. The control parameters are iteratively optimized using the gradient descent method. Specifically, the gradient of the objective function with respect to the current control parameters is calculated to determine the direction of parameter adjustment. The control parameters are then adjusted along the gradient direction to gradually reduce the deviation integral, and the temperature change after adjustment is monitored in real time. A regional temperature synchronicity index is introduced, namely, the temperature difference between regions is ≤2℃, which is used as a constraint condition. At the same time, the allocation efficiency of heating / cooling resources is used as the objective function to construct a quadratic programming model. The quadratic programming algorithm is used to solve the quadratic programming model to calculate the optimal heating / cooling resource allocation scheme. Based on the solution results, the heating power or cooling flow rate is allocated to each area to achieve synchronous temperature regulation in each area.

8. The ultra-low temperature cold start thermal management system for hydrogen fuel cell vehicles according to claim 7, characterized in that: The actuator response module specifically includes: The actuator response module receives control signals from the thermal management control module in real time, including power adjustment commands for the heating or cooling system. It preprocesses the received control signals and checks their integrity and validity, confirming whether the control signals conform to the expected command format and range. If the command fluctuation is <1% within 5 consecutive sampling periods, the current command value is locked. If the temperature change rate is >2℃ / s, the heating / cooling intensity command is responded to first. If the regional temperature difference is >1.5℃, the resource allocation command is responded to first. The processed control signal is converted into a specific drive signal to adjust the working state of the actuators in the heating and cooling systems. For the actuators in the heating system, rapid heating is achieved by changing the power output of the heating element. For the actuators in the cooling system, rapid cooling is achieved by adjusting the fan speed and water pump flow parameters. The actual operating status of the actuator is continuously monitored, including power output, speed and flow parameters. The status information is fed back to the thermal management control module in real time through the feedback loop. The difference between the actual status and the target status is compared, and the drive parameters of the actuator are dynamically optimized using an adaptive control algorithm. At the same time, the operating status of the actuator is monitored in real time, and any faults or abnormalities are detected and handled.

Images